Standard 12-lead Electrocardiography Research Articles

Diagnostic Accuracy of Apple Watch Electrocardiogram for Atrial Fibrillation: A Systematic Review and Meta-Analysis.

Electrocardiography (ECG) is the gold standard for the diagnosis of atrial fibrillation (AF). Recently, smartwatches like the Apple Watch have emerged as a promising, user-friendly device for rapid detection and diagnosis of AF, but the reliability and diagnostic accuracy still remain controversial. The purpose of this study was to perform a systematic review and diagnostic test accuracy meta-analysis evaluating the diagnostic performance of the Apple Watch ECG in detecting AF. The literature search was conducted on PubMed, Embase, and Cochrane Library through April 2024 for studies comparing the diagnostic accuracy of Apple Watch to standard 12-lead ECG. Statistical analysis was performed using R Software version 4.4.0 and OpenMeta[Analyst]. Pooled analyses of sensitivity, specificity, and area under the receiver operating characteristic curve were determined along with their 95%CIs. The quality of studies was analyzed using the QUADAS-2 tool. The meta-analysis included 11 studies comprising 4,241 participants. Their mean age was 62.56±3.92years, and 28% of the patients were females. The pooled sensitivity and specificity of the Apple Watch for detecting AF were 94.8% (95%CI: 91.7% to 96.8%; I2=67%) and 95% (95%CI: 88.6% to 97.8%; I2=88%), respectively. The area under the receiver operating characteristic curve was 0.96 (95%CI: 0.92-0.97). The Apple Watch ECG carries high accuracy in detecting atrial fibrillation, providing a convenientdiagnostic option for patients.

Deep learning-enabled electrocardiogram assessment of valvular heart disease

Abstract Background Valvular heart disease is a highly prevalent condition that contributes significantly to cardiovascular morbidity and mortality. Echocardiography is the gold-standard for valvular disease evaluation; however, diagnosis may be delayed due to limited resources or expertise. Deep learning analysis of electrocardiography (ECG) has demonstrated the ability to identify subtle structural and functional abnormalities within the cardiovascular system. Purpose The aim of this study was to evaluate the accuracy of a deep learning algorithm to identify valvular heart disease from a standard 12-lead ECG. Methods From 2008 to 2019, a total of 27,689 patients who were admitted to the Medical Center with an echocardiogram and ECG performed within 14 days of each other were included in the study. We trained a convolutional neural network to identify the presence of moderate or severe aortic stenosis (AS), aortic regurgitation (AR), mitral regurgitation (MR), and/or tricuspid regurgitation (TR) using a 12-lead ECG. Model performance was assessed using area under the receiver-operating characteristic (AUROC). Patients were randomly divided into development (n = 22,151; 80%) and independent validation sets (n = 5,538; 20[AN1] %). Data used for the study was collected from two open access databases, MIMIC-IV-ECG and MIMIC-IV-Note. Results Mean age of the cohort was 65.9 ± 16.6 years old and 51% were female. On the independent validation dataset, AS was present in 126 (2.3%) of patients, AR in 51 (1%), MR in 337 (6.1%), and TR in 450 (8.1 %) patients. During validation, the model accurately identified AS, AR, MR, and TR with AUROCs of 0.80 (95% CI 0.77-0.83), 0.74 (95% CI 0.69-0.80), 0.86 (95% CI 0.84-0.88), and 0.85 (95% CI 0.83-0.87), respectively (Table 1). Test characteristics were dependent on underlying prevalence and selected sensitivity levels. For a composite of any of AS, AR, MR, or TR, the model achieved a positive predictive value of 28% with 79.4% sensitivity. Conclusion A deep learning-enabled ECG demonstrates robust performance to identify patients living with valvular heart disease. This model may serve as a simple and promising tool for improving the early detection of valvular heart disease, showcasing the potential for an early development valvular disease screening program.

Electrocardiographic Assessment of National-Level Triathletes: Sinus Bradycardia and Other Electrocardiographic Abnormalities.

High-intensity endurance training induces specific cardiac adaptations, often observed through electrocardiographic (ECG) changes. This study investigated the prevalence of ECG abnormalities in national-level Australian triathletes compared to sedentary controls. A cross-sectional observational study was conducted involving 22 triathletes and 7 sedentary controls. Standard 12-lead ECGs assessed resting heart rate, ECG intervals, and axis deviation. Peak oxygen consumption was evaluated in triathletes to correlate with ECG indices and left ventricular mass, derived via echocardiography. Triathletes exhibited significantly lower resting heart rates (53.8 vs. 72.1 bpm, -34%, p = 0.04), shorter QRS durations (0.088 vs. 0.107 ms, -21.6%, p = 0.01), and longer QT intervals (0.429 vs. 0.358 ms, +16.6%, p = 0.01) compared to controls. Sinus bradycardia was present in 68.2% of triathletes, with varying severity. First-degree atrioventricular block was identified in 13.6% of athletes, and left ventricular hypertrophy was confirmed in 18 triathletes via echocardiography. A significant positive relationship was identified between VO2peak and left ventricular mass (r = 0.68, p = 0.003). National-level triathletes exhibited ECG and structural cardiac adaptations consistent with high-intensity endurance training. Echocardiography is recommended for the accurate identification of LVH. These findings highlight the need for comprehensive cardiac evaluation in athletes to distinguish between physiological and pathological adaptations.

Prevalence of Atrial Fibrillation in Older Adults with Diabetes Mellitus: A Cross-Sectional Study

Background: Atrial fibrillation (AF) is a common arrhythmia in older adults, with diabetes mellitus (DM) serving as a significant risk factor. The interplay of aging, glycemic control, and comorbid conditions such as hypertension and chronic kidney disease (CKD) heightens the prevalence and associated risks of AF in this population. Objective: To determine the prevalence of AF in older adults with DM and identify key associated risk factors. Methods: This cross-sectional study included 137 older adults with DM recruited from clinical settings. Participants underwent clinical evaluations, including demographic data collection, glycemic control assessment (HbA1c), and screening for comorbidities. Standard 12-lead electrocardiography was used to detect AF, with all diagnoses confirmed by certified cardiologists. Statistical analyses, including chi-square tests and multivariate logistic regression, were performed using SPSS version 25. Results: The overall prevalence of AF was 11.7% (16/137), with 43.8% (7/16) newly diagnosed cases and 31.3% (5/16) asymptomatic AF. Advanced age (OR: 1.45; 95% CI: 1.11–1.88; p=0.005) and CKD (OR: 2.87; 95% CI: 1.33–6.21; p=0.007) were significant independent predictors. Conclusion: The study highlights a significant prevalence of AF, including silent cases, in older adults with DM, emphasizing the need for routine screening and early intervention in high-risk populations.

PATCH (Preferred Attachment Strategy for Optimal Electrocardiograms)-1 Study.

12-Lead electrocardiography (ECG) is among the most frequently performed tests in medical practice. Despite its pivotal role in diagnostic and treatment decisions, baseline artifacts and errors in lead placement are common. The PATCH (Preferred Attachment Strategy for Optimal Electrocardiograms)-1 study enrolled patients with stable cardiovascular disease and a clinical indication for an ECG. Each participant underwent both a standard (S) 12-lead ECG and a patch (P) ECG (EKG-Patch™) during one routine ambulatory clinic visit. The P-ECG has an all-in-one design with built-in lead wires attached to pre-positioned electrodes. An experienced clinical research coordinator performed all ECGs. Each was interpreted by an experienced cardiologist blinded to the method of ECG. A total of 200 participants (67.4 ± 14.9years; range: 21-95years) (women 44%) had P- and S-ECGs. Common clinical indications included coronary artery disease (40.5%), essential hypertension (14.0%), heart failure (10.5%), atrial fibrillation (10.0%) and valvular heart disease (6.5%). Many participants had more than one indication. The P-ECG provided a tracing in 1.4 ± 0.5min compared to 2.4 ± 0.5min with the S-ECG (p < 0.001). Most participants either preferred the P-ECG (47%) or did not have a preference (52%). Baseline artifacts that impacted interpretability were detected in 13 (6.5%) P-ECGs and 30 (15.0%) S-ECGs (p = 0.006). Heart rhythm, rate, conduction, axis, intervals (PR, QRS, QT, and QTc) and ST-T wave findings did not differ between P-and S-ECGs. In conclusion, the P-ECG was preferred among participants, had fewer baseline artifacts than the S-ECG, and provided a rapid and reproducible ECG in patients with stable cardiovascular disease in an ambulatory clinic setting.

Are adolescents with premenstrual disorder at risk for cardiac arrhythmias?

One of the most commonly experienced symptoms of premenstrual disorder (PMD) is anxiety, and there is a notable rise in sympathomimetic activity in this patient group. Studies have linked fluctuations in systemic autonomic tone to electrocardiography (ECG) changes. This study aims to investigate the relationship between anxiety, a common symptom of PMD, and alterations in QT dispersion (QTd) and P-wave dispersion (Pd) in adolescent females. This cross-sectional study included female adolescents aged 12-18 with regular menstruation for at least 3 months. Participants completed the premenstrual syndrome scale (PMSS) and were divided into two groups, PMD and control, according to the PMSS score. A standard 12-lead body surface ECG was performed and QTd and Pd values were determined in each participant. Of the 43 participants, 27 were categorized into the PMD group, with a mean age of 15.15 ± 1.43 years. Age at menarche and menstrual cycle patterns were comparable between the PMD and control groups. Statistical analysis revealed significantly higher Pmin (p = 0.010) and Pd values (p < 0.001) in the PMD group compared to controls. A positive correlation between PMSS scores and Pd (p = 0.049) was also observed. Changes in atrial conduction and ventricular repolarization due to the pathophysiology of PMD may increase the risk of developing atrial and ventricular tachyarrhythmias over time. Screening patients with PMD using an ECG may be useful in identifying potentially at-risk adolescents.

Evaluation of cardiac clues in patients admitted to pediatric cardiology outpatient clinic with syncope

Background: In our study, we aimed to determine the incidence rates of children admitted to the pediatric cardiology outpatient clinic with syncope according to their etiologies; and especially to reveal the clues that distinguish cardiac syncope cases from other cases. Materials and Methods: The study was conducted by obtaining the information of 795 children aged 5-17 years who were diagnosed with syncope in the pediatric cardiology outpatient clinic of our tertiary university hospital between 01.01.2021 and 01.06.2024 from the data in our hospital automation system. Medical history of the patient and his/her family, syncopal event, physical examination findings, 12-lead electrocardiography (ECG), echocardiography, 24-hour rhythm holter and exercise ECG records were analyzed. Results: Cardiac syncope was 14.5% (10.8% arrhythmia and 3.7% structural heart disease) while noncardiac syncope was 85.5% (VVS 60.6%, OH 18.6%, situational 1% and 4.8% idiopathic). The most common conditions associated with cardiac syncope were a history of arrhythmia and heart disease, a family history of sudden death at a young age, and syncope associated with exercise-palpitations-chest pain. Rhythm holter test had a low diagnostic rate, while exercise ECG test had a high diagnostic rate. Conclusion: It is important to diagnose cardiac syncope as it can cause sudden death. Standard 12-lead ECG, echocardiography and rhythm holter examination should be performed in all suspected patients; exercise ECG, head-up tilt test, genetic arrhythmia/cardiomyopathy investigations and electrophysiologic study should be performed in selected cases. In addition, simultaneous ECG monitoring during electroencephalography (EEG) examination in patients presenting with atonic seizures will be very useful in terms of clarifying the etiology.

Analysis of abnormalities in cardiac arrhythmia based on 12 - LEAD electrocardiography

Myocardial Infarction otherwise called heart attack occurs in human beings when blood flow decreases or stops to a part of the heart which in turn damages the heart muscle. Prediction of abnormalities in cardio arrhythmia disease is done by using standard 12-lead Electrocardiography (ECG) signals, which also detects Posterior Myocardial Infarction (PMI). The QRS complex is the merged output of different parts of graphical deflection seen on a typical Electro Cardio Gram (Electrocardiography). The main purpose of the paper is to monitor and analyze particularly the Rpeak upward deflections from the QRS complex. Denoising the ECG signal is done by butter worth filter. The denoised signals are used to detect R peaks and image plotting is done by segmentation. R peak images are used to classify the abnormalities in Myocardial Infarction (MI) with the help of the CNN image processing technique. The publicly available PTB diagnostic dataset is used to classify the abnormalities in PMI. The detection of the R peaks is used to guide Cardiologists must advance the Percutaneous Coronary Intervention treatment. Prediction has been done using probability weighted average method. Troponin level has been calculated to evaluate a person's health condition which also supports in close prediction of diseases and abnormalities. From experimental analysis of proposed Probability weighted average method in troponin level (PWAMT), the accuracy scores in the ensemble model were found to be 86 % respectively. The running of algorithm took 250 s–300 s to execute the program and display the prediction results.

PREVALENCE AND ASSOCIATED PROGNOSIS OF ELECTROCARDIOGRAPHIC FINDINGS IN HYPERTENSIVE PATIENTS. AN ANALYSIS OF A 5-YEAR FOLLOW-UP STUDY

Objective: Various electrocardiographic abnormalities may be identified in hypertensive patients, but their prognostic significance has not been sufficiently studied. We investigated the presence of diverse ECG findings in a hypertensive population and their predictive ability for cardiovascular disease. Design and method: We studied 1851 white Caucasian hypertensive patients (age 58±12years, 51% females) free of cardiovascular disease for a mean period of 5.3±3.4 years. At baseline, all patients underwent standard 12-lead electrocardiography. Left ventricular hypertrophy (LVH) criteria were assessed using both the Sokolow and the Cornel-Voltage formulas. An interventricular conduction delay (IVCD) was defined as a QRS &gt;110msec in the absence of a bundle branch block (BBB). QRS fragmentation was identified as notches in the QRS complex not related to BBB. The QTc interval was considered prolonged if &gt; 440ms in men and &gt;460ms in women. ST depression was defined as &gt;1 mm in depth. The outcome studied was the incidence of cardiovascular morbidity set as the composite of non-fatal coronary artery disease and stroke. Results: LVH criteria were fulfilled in 7% with the Sokolow formula and in 5.3% with Cornell Voltage criteria. A prolonged PR was evident in 6.3%. An IVCD, a left BBB and a right BBB were observed in 9%, 4.1% and 1% of the population respectively. QRS fragmentation was identified in 18% of the study population. An early transition zone was found in 30% of the population and a late transition zone in 19%. QTc was prolonged in 9.8% of cases. Prevalence of TWI was 3.8%, of which 39% was anterior TWI, 73% was lateral TWI and 11% was inferior TWI. Incidence of the composite endpoint during follow-up was 4%. Cox regression analysis revealed that only prolonged QTc (HR: 1.86, 95% CI: 0.97-3.54, p=0.06) and presence of TWI (HR: 2.6, 95% CI: 1.1-5.9, p=0.025) were associated with the composite endpoint. In multivariate models controlling for standard confounders the association with TWI was overall sustained. Conclusions: Among hypertensive patients without cardiovascular disease, ECG abnormalities are frequent. A prolonged QTc and T wave inversion seem to exhibit prognostic significance for cardiovascular events.

PREVALENCE AND PROGNOSTIC VALUE OF T-WAVE INVERSION IN HYPERTENSIVE PATIENTS: A 5-YEAR FOLLOW-UP STUDY

Objective: Data on prevalence and associated prognosis of repolarization abnormalities among hypertensive patients are limited. We investigated the presence and extent of ST-segment and T-wave changes in a hypertensive population and their predictive ability for cardiovascular disease. Design and method: We studied 1851 white Caucasian hypertensive patients (age 58±12years, 51% females) without a history of cardiovascular disease for a mean period of 5.3±3.4 years. At the baseline examination, all patients underwent standard 12-lead electrocardiography. T-wave inversion (TWI) was defined as T-wave deflection &gt; -0.1 mV in &gt; 2 contiguous leads, unless associated with bundle branch block. Anterior, lateral, or inferior TWI was defined as TWI in leads V2-V4 or V5, V6, I, AVL or II, aVF respectively. The depth in millimeters of TWI in each lead was recorded and the maximum depth per location was calculated. ST depression was defined as &gt;1 mm in depth in two or more contiguous leads. During follow-up, patients underwent clinic visits at least yearly for management of hypertension and risk factors. The outcome studied was the incidence of cardiovascular morbidity set as the composite of non-fatal coronary artery disease and stroke. Results: In the entire population, prevalence of TWI was 3.8%, of which 39% presented with anterior TWI, 73% with lateral TWI and 11% with inferior TWI. ST depression was observed in 3.6% of patients (anterior in 0.8%, inferior in 0.9% and lateral in 2.6%). Incidence of the composite endpoint during follow-up was 4%. Cox regression analysis revealed that presence of TWI was associated with a significantly greater risk for cardiovascular events (HR: 2.6, 95% CI: 1.1-5.9, p=0.025). The association was stronger for lateral TWI (HR: 3.3, 95%: CI: 1.34-8.30, p=0.01) compared to other locations. In multivariate models controlling for standard confounders these associations were overall sustained. Depth of TWI and presence of ST depression were not associated with cardiovascular risk. Conclusions: Among hypertensive patients without cardiovascular disease, TWI is infrequent but significantly associated with future cardiovascular events. Lateral TWI carries the worse prognosis.

Edge AI Model Deployed for Real-Time Detection of Atrial Fibrillation Risk during Sinus Rhythm.

Objectives: The study aimed to develop a deep learning-based edge AI model deployed on electrocardiograph (ECG) devices for the real-time detection of atrial fibrillation (AF) risk during sinus rhythm (SR) using standard 10 s, 12-lead electrocardiograms (ECGs). Methods: A novel approach was used to convert standard 12-lead ECGs into binary images for model input, and a lightweight convolutional neural network (CNN)-based model was trained using data collected by the Japan Agency for Medical and Research Development (AMED) between 2019 and 2022. Patients over 40 years old with digital, SR ECGs were retrospectively enrolled and divided into AF and non-AF groups. The data labeling was supervised by cardiologists. The dataset was randomly allocated into training, validation, and internal testing datasets. External testing was conducted on data collected from other hospitals. Results: The best-trained model achieved an AUC of 0.82 and 0.80, sensitivity of 79.5% and 72.3%, specificity of 77.8% and 77.7%, precision of 78.2% and 76.4%, and overall accuracy of 78.6% and 75.0% in the internal and external testing datasets, respectively. The deployed model and app package utilized 2.5 MB and 40 MB of the available ROM and RAM capacity on the edge ECG device, correspondingly. The processing time for AF risk detection was approximately 2 s. Conclusions: The model maintains comparable performance and improves its suitability for deployment on resource-constrained ECG devices, thereby expanding its potential impact to a wide range of healthcare settings. Its successful deployment enables real-time AF risk detection during SR, allowing for timely intervention to prevent AF-related serious consequences like stroke and premature death.

Autonomic cardiac function in children and adolescents with long COVID: a case-controlled study

Although the mechanisms underlying the pathophysiology of long COVID condition are still debated, there is growing evidence that autonomic dysfunction may play a role in the long-term complications or persisting symptoms observed in a significant proportion of patients after SARS-CoV-2 infection. However, studies focused on autonomic dysfunction have primarily been conducted in adults, while autonomic function has not yet been investigated in pediatric subjects. In this study, for the first time, we assessed whether pediatric patients with long COVID present abnormalities in autonomic cardiac function. Fifty-six long COVID pediatric patients (mean age 10.3 ± 3.8 y) and 27 age-, sex-, and body surface area-matched healthy controls (mean age 10.4 ± 4.5y) underwent a standard 12-lead electrocardiography (ECG) and 24-h ECG Holter monitoring. Autonomic cardiac function was assessed by time-domain and frequency-domain heart rate variability parameters. A comprehensive echocardiographic study was also obtained by two-dimensional echocardiography and tissue Doppler imaging. Data analysis showed that pediatric patients with long COVID had significant changes in HRV variables compared to healthy controls: significantly lower r-MSSD (root mean square of successive RR interval differences, 47.4 ± 16.9 versus 60.4 ± 29.1, p = 0.02), significant higher values VLF (very low frequency, 2077.8 ± 1023.3 versus 494.3 ± 1015.5 ms, p = 0.000), LF (low frequency, 1340.3 ± 635.6 versus 354.6 ± 816.8 ms, p = 0.000), and HF (high frequency, 895.7 ± 575.8 versus 278.9 ± 616.7 ms, p = 0.000). No significant differences were observed between the two groups both in systolic and diastolic parameters by echocardiography. Conclusion: These findings suggest that pediatric patients with long COVID have an imbalance of cardiac autonomic function toward a relative predominance of parasympathetic tone, as already reported in adult patients with long COVID. Further studies are needed to clarify the clinical significance of this autonomic dysfunction and demonstrate its role as a pathophysiological mechanism of long COVID, paving the way for effective therapeutic and preventive strategies.What is Known:• Long Covid in children has been described globally, but studies have mostly focused on collecting the temporal evolution of persisting symptoms.What is New:• Cardiac autonomic imbalance toward a relative predominance of parasympathetic tone is a mechanism underlying Long Covid in children, as also described in adults.

The association between continuous metabolic syndrome score and its components with electrocardiographic abnormalities in community-dwelling older adults: the Bushehr elderly health (BEH) program

BackgroundMetabolic syndrome (MetS) known as a risk factor for cardiovascular diseases (CVDs) has developed into a major source of health issue, especially for the elderly. In the present study, we investigated the association between continuous MetS (cMetS) score and its components with electrocardiographic (ECG) abnormalities in the community-dwelling older adults.MethodsThis cross-sectional study is derived from the second phase of BEH cohort study which is conducted on individuals aged over 60 years old. Standard 12-lead ECGs were recorded and coded by qualified physicians and continuous values of metabolic syndrome risk scores (cMetS) were measured. Data regarding socio-demographic, medical history, and lifestyle variables were collected by trained interviewers. The multinomial regression analysis was used to investigate the relationship between cMetS and its components with ECG abnormalities in the included participants.Results2426 individuals (mean age ± standard deviation: 69.30 ± 6.33 years) were included in the final analysis. Overall, 22.5% of the participants showed ECG abnormalities. Among these, 8.0% (n = 139) of participants had minor and 14.6% (n = 354) had major ECG abnormalities. In the final models, cMetS (OR = 1.04), mean arterial pressure (MAP((OR = 1.01), and higher fasting blood glucose (FBG) (OR = 1.01) increased the risk of ECG abnormalities (p < 0.05). Also, cMetS (OR = 1.05) and MAP (OR = 1.02) were associated with an increased risk of major ECG abnormalities (p < 0.05).ConclusionMetS and MAP were significantly associated with ECG abnormalities. The results of the present study suggest that ECG screening in the older population with MetS could potentially help to detect those at the higher risk of CVDs.

Qualitative and Quantitative Electrocardiogram Parameters in a Large Cohort of Children with Duchenne Muscle Dystrophy in Comparison with Age-Matched Healthy Subjects: A Study from South India.

Electrocardiography (ECG) remains an excellent screening tool for cardiac assessment in Duchenne muscular dystrophy (DMD), but an accurate interpretation requires comparison with age-matched healthy controls. We examined various ECG parameters in children with DMD, in comparison with age-matched controls. Standard 12-lead ECG tracings of serial patients were screened for quality and selected. Controls were healthy, age-matched school-going children. Both quantitative and qualitative ECG parameters were analyzed. After screening, ECGs from 252 patients with DMD (8.32 ± 3.12 years, 2-21 years) and ECGs from 151 age-matched healthy controls (9.72 ± 2.23, 4-19 years) were included. A significantly higher heart rate, shorter R-R interval, and taller R wave in V1 were seen across all age group of DMD in comparison to controls, with the difference increasing with age. While QT prolongation was seen in all age groups of DMD, QTc prolongation was seen only at 10 years or more. Incomplete right bundle branch block (RBBB) and pathological Q waves in inferolateral leads were exclusive in DMD, with the latter declining with age. Evidence for left ventricular (LV) pathology, such as tall R in V5/V6, increase in SV1 + RV6 height, and QRS complex duration, were seen only in the age group of 10 years or more. Stratification based on age and comparison with age-matched healthy subjects showed that several ECG parameters were influenced by age, and it also identified age-dependent evidence for LV pathology and QTc prolongation in DMD.

Electrocardiography score based on the Minnesota code classification system predicts cardiovascular mortality in an asymptomatic low-risk population

Background The use of a single abnormal finding on electrocardiography (ECG) is not recommended for stratifying the risk of cardiovascular (CV) events in low-risk general populations because of its low discriminative power. However, the value of a scoring system containing multiple abnormal ECG findings for predicting CV death has not been sufficiently evaluated. Methods In a prospective community-based cohort study, 8417 participants without atherosclerotic CV diseases (ASCVDs) and any related symptoms were followed for 18 years. The standard 12-lead ECGs were recorded at baseline and the ECG findings were categorized using the Minnesota code classification. CV deaths were defined as death from myocardial infarction (MI), chronic ischemic heart disease, heart failure, fatal arrhythmia, cerebrovascular event, pulmonary thromboembolism, peripheral vascular disease and sudden cardiac arrest and identified using the Korean National Statistical Office (KOSTAT) database. Results In a multivariate Cox proportional hazard (CPH) model, major and minor ST-T wave abnormalities, atrial fibrillation (AF), Q waves in the anterior leads, the lack of Q waves in the posterior leads, high amplitudes of the left and right precordial leads, left axis deviation and sinus tachycardia were associated with higher risks of CV deaths. The ECG score consisted of these findings showed modest predictive values represented by C-statistics that ranged from 0.632 to 760 during the follow-up and performed better in the early follow-up period. The ECG score independently predicted CV death after adjustment for relevant covariates in a multivariate model, and improved the predictive performance of the 10-year ASCVD risk estimator and a model of conventional risk factors including age, diabetes and current smoking. The combined ECG score (Harrell’s C-index: 0.852, 95% confidence interval [CI], 0.828–0.876) composed of the ECG score and the conventional risk factors outperformed the 10-year ASCVD risk estimator (Harrell’s C-index: 0.806; 95% CI, 0.780–0.833) and the model of the conventional risk factors (Harrell’s C-index: 0.841, 95% CI, 0.817–0.865) and exhibited an excellent goodness of fit between the predicted and observed probabilities of CV death. Conclusions The ECG score could be useful to predict CV death independently and may add value to the conventional CV risk estimators regarding the risk stratification of CV death in asymptomatic low-risk general populations.

Obesity and Cardiac Conduction Block Disease in China

Although a high body mass index (BMI) has been found to be associated with increased risk of cardiac conduction block (CCB) in older adults, no further studies have investigated the association between obesity and CCB in the general population. To investigate the association between obesity and CCB, including its subtypes. This cohort study used data from participants in the Kailuan Study in China (2006-2018) who had completed a physical examination in 2006 (baseline) and had not experienced CCB before baseline. Data analysis was conducted from March to September 2023. Obesity status was defined by BMI in 3 groups: normal weight (18.5 to <24), overweight (24 to <28), and obesity (≥28). The primary outcome was CCB, which was diagnosed from standard 12-lead electrocardiography. The primary end point included high-grade atrioventricular block (HAVB), complete right bundle branch block, complete left bundle branch block, left anterior fascicular block (LAFB), and left posterior fascicular block. First-degree atrioventricular block (FAVB), second-degree type 1 AVB, HAVB, complete and incomplete right and left bundle branch block, LAFB, and left posterior fascicular block were considered separately as secondary end points. Among 86 635 participants (mean [SD] age, 50.8 [11.9] years; 68 205 males [78.7%]), there were 33 259 individuals with normal weight (38.4%), 37 069 individuals with overweight (42.8%), and 16 307 individuals with obesity (18.8%). The mean (SD) follow-up was 10.6 (3.07) years. In the multivariable Cox proportional hazards regression analysis, obesity was associated with an increased risk of incident CCB (hazard ratio [HR], 1.21; 95% CI, 1.04-1.42) vs normal BMI. In secondary analysis, obesity was associated with an increased risk of FAVB (HR, 1.44; 95% CI, 1.21-1.73), HAVB (HR, 1.99; 95% CI, 1.03-3.82), and LAFB (HR, 1.29; 95% CI, 1.03-1.62) vs normal BMI. There was no association between obesity and other CCB subtypes. Obesity was associated with a greater increase in risk of CCB vs normal BMI in older (aged ≥65 years; HR, 1.44; 95% CI, 1.05-1.96) vs younger (aged <65 years; HR, 1.13; 95% CI, 0.96-1.34) participants (P for interaction < .001) and those with diabetes (HR, 2.16; 95% CI, 1.24-3.76) vs without diabetes (HR, 1.19; 95% CI, 1.02-1.39) (P for interaction = .02). This study found that obesity was associated with an increased risk of CCB, with greater increases in risk for FAVB, HAVB, and LAFB. Individuals who were older and those who had diabetes had larger increases in risk.

5-lead 3D-vectorcardiography differentiates between high and low cardiovascular risk profiles in patients with suspected or know coronary heart disease

Abstract 5-lead 3D-vectorcardiography (3D-VCG), including a dorsal electrode with ensemble of artificial neural networks (ANN) offers additional information over standard 12-lead electrocardiography (ECG) in the detection of cardiac ischaemia. Artificial Intelligence (AI) and access to a massive global clinical data repository have the potential to boost the performance of VCG beyond conventional techniques. VCG offers ease-of-use at rest and is therefore a promising candidate for becoming a new screening tool for coronary artery diseases (CAD). We, thus, tested the hypothesis of 3D-VCG being able to differentiate between patients with lower and high risk of cardiovascular disease (CVD) and identify those requiring coronary interventions. In this exploratory study, we analysed patients in a national multicentre trial. Patients were recruited from general cardiologists’ praxis and radiologist centre with patients referred for further diagnosis of suspected or confirmed CVD. Based on the Perfusion (P)-Factor of the 5-lead 3D- vectorcardiography, including 731 parameters, e.g., QRS-T angle and in-house features calculated in time and frequency domains, such as beat moments a P-Index is calculated. Based on the P-Index, patients were either classified as high, medium, or low risk for CVD (medium + high defined as high CVD-risk). Confirmation of CAD was performed according to the practitioners’ discretion blinded to the P-Index. Number of risk factors (mod. PROCAM score) were compared between the high- and low-risk group using an independent t-test. The 468 patients in this sample (m:w 61:39, age: 66 [40-87] years) showed 3.6 [0 - 7] CVRF, 16% had arrhythmias or conduction disturbances (AF, PM, BBB), 24% pts. had consecutive PCI or CABG. 62% were classified as low while 38% were classified as high risk for CVD by the P-Index. Number of cardiovascular risk factors was significantly higher in the high-risk CVD-group as defined by P-Index compared to low CVD-risk (4.0 [3.0 – 5.0] vs. 3.5 [2.0 – 4.0], p &amp;lt; 0.05). P-Index differentiated between suspected CVD with or without consequent PCI or CABG (Chi2 = 4.02, p&amp;lt;0.05). The AI-based 3D-VCG is an innovative diagnostic tool that can help determine a patient's cardiovascular risk profile in resting condition for clinical and research purposes. Furthermore, the P-Index identified those with significant stenoses in need for coronary intervention and may thus be a further scalable screening method to differentiate patients with consequent interventional approach or need for risk modification. These preliminary data will have to be confirmed in a prospective, large-scale performance study to verify the diagnostic accuracy.

Abstract 16473: Validation of the Artificial Intelligence-Based 5-Lead 3D Vectorcardiography in Comparison to the 12-Lead ECG in a Mixed Population

Introduction: Artificial Intelligence-based 5-lead 3D-vectorcardiography (5L3DVCG-AI) offers additional information over 12-lead electrocardiography (ECG) in the detection of significant coronary stenoses. 5L3DVCG-AI is under investigation as a new screening tool for coronary vascular disease (CVD). Hypothesis: We tested the hypothesis of variables from the reconstructed “12-lead ECG” (5L12L-ECG, modified Dower transformation) corresponding with the standard 12-lead ECG (ECG). Methods: In this monocentric exploratory retrospective study, raw data of 331 patients with 5L3DVCG-AI and ECG were included. Cardiac pathology (CP) was categorised as exclusion of any CP (control), mild CP or overt CP by 2 independent cardiologists. The following variables were compared: RR-interval, P, PQ, QRS, QT, QTcB, QTcF, QRS-morphology, and ST-morphology. Cardiovascular risk factors (CVRF) were quantified with the modified PROCAM score. Results: From 331 patients (m:w 60:40%, 50.0 ± 19.8 years) of mixed ethnicity and moderate CVRF (2.1 ± 1.2), 70% were controls, 21% had mild CP and 9% overt CP. All variables from reconstructed 5L12L-ECG correlated to the corresponding individual variables from ECG (r= 0.49 to 0.7, p&lt;0.001). With identical RR-intervals in both methods, all defined variables were significantly, but irrelevantly or mildly (Cohen’s d) different in 5L12L-ECG compared to ECG (P 106 ± 12 vs. 109 ±20 ( d =0.3), PQ 152 ± 24 vs. 159 ± 26 ( d =0.3), QRS 105 ± 16 vs. 97 ± 14 ( d =0.7), QT 380 ± 33 vs. 396 ± 27 ( d =0.46), QTcB 432 ± 31 vs. 426 ± 25 ( d =0.57), QTcF 414 ± 26 vs. 416 ± 19 ( d =0.53). 5L3DVCG-AI was able to distinguish between controls and patients with CVD (Sensitivity 78%, Specificity 66%, p=0.01). Comparing heart axis, there was a small, but significant difference with a significant correlation between methods (r=0.30, p&lt;0.01). Conclusions: The easy to use 5-lead ECG may thus be used in clinical practice to reconstruct valid 12-lead ECG curves without major training or expertise. Additionally, 5L3DVCG-AI can identify persons at risk for CVD. Shorter values for the defined variable will have to be considered when interpreting 5L12L-ECG and separate “normal” value ranges will be given and validated in the ongoing prospective large-scale performance clinical trials.

Abstract 16682: Artificial Intelligence Predicts All-Cause and Cardiovascular Mortalities Using 12-Lead Electrocardiography

Introduction: Electrocardiography (ECG) can be easily obtained at a low cost and includes voltage and time interval representing heart conditions. We hypothesized that artificial intelligence (AI) detects a subtle abnormality in 12-lead ECG and may predict individual mortality. Methods: Among 502,411 population in UK Biobank, 42,096 individuals had 12-lead ECG from 2013 to 2022. Among 41,572 survival group, after adjusting the following inclusion criteria; normal sinus rhythm, age under 60 years, PR interval 120~200ms, QTc interval 350~460ms, and QRS duration 70~100ms, 4,512 individuals were enrolled in this study. We developed and tested convolutional neural network (CNN) model to predict all cause death, cardiovascular (CV) death, or sudden cardiac arrest (SCA). The study population were divided into train (80%), validation (10%), and test (20%) set. Results: Among 4,512 patients with median 3.7 years [IQR; 2.7-5.1] of follow-up, the rate of all-cause mortality was 11.6% (524). In overall study population, median age was 55.5 years and proportion of male sex was 42.2%. The patients with all-cause death were older (p&lt;0.001) and had more comorbidities (p&lt;0.001). In the train set, CNN model showed 0.93 in AUC for predicting all-cause death. In the test set, CNN model showed consistent good performance power (AUC 0.90) for all-cause death. In subgroup analysis, 102 of 4153 (2.46%) and 57 of 4065 (1.40%) patients experienced CV death and SCA, respectively. The performance power in test set were 0.90 in AUC for CV death and 0.87 in AUC for SCA. Conclusions: AI detects and predicts future all-cause death, CV death, and SCA in median of 2.6 years by analyzing standard 12-lead ECG in generally looking normal sinus rhythm

Artificial intelligence-enhanced 12-lead electrocardiography for identifying atrial fibrillation during sinus rhythm (AIAFib) trial: protocol for a multicenter retrospective study.

Atrial fibrillation (AF) is the most common arrhythmia, contributing significantly to morbidity and mortality. In a previous study, we developed a deep neural network for predicting paroxysmal atrial fibrillation (PAF) during sinus rhythm (SR) using digital data from standard 12-lead electrocardiography (ECG). The primary aim of this study is to validate an existing artificial intelligence (AI)-enhanced ECG algorithm for predicting PAF in a multicenter tertiary hospital. The secondary objective is to investigate whether the AI-enhanced ECG is associated with AF-related clinical outcomes. We will conduct a retrospective cohort study of more than 50,000 12-lead ECGs from November 1, 2012, to December 31, 2021, at 10 Korean University Hospitals. Data will be collected from patient records, including baseline demographics, comorbidities, laboratory findings, echocardiographic findings, hospitalizations, and related procedural outcomes, such as AF ablation and mortality. De-identification of ECG data through data encryption and anonymization will be conducted and the data will be analyzed using the AI algorithm previously developed for AF prediction. An area under the receiver operating characteristic curve will be created to test and validate the datasets and assess the AI-enabled ECGs acquired during the sinus rhythm to determine whether AF is present. Kaplan-Meier survival functions will be used to estimate the time to hospitalization, AF-related procedure outcomes, and mortality, with log-rank tests to compare patients with low and high risk of AF by AI. Multivariate Cox proportional hazards regression will estimate the effect of AI-enhanced ECG multimorbidity on clinical outcomes after stratifying patients by AF probability by AI. This study will advance PAF prediction based on AI-enhanced ECGs. This approach is a novel method for risk stratification and emphasizes shared decision-making for early detection and management of patients with newly diagnosed AF. The results may revolutionize PAF management and unveil the wider potential of AI in predicting and managing cardiovascular diseases. The study findings will be published in peer-reviewed publications and disseminated at national and international conferences and through social media. This study was approved by the institutional review boards of all participating university hospitals. Data extraction, storage, and management were approved by the data review committees of all institutions. [cris.nih.go.kr], identifier (KCT0007881).